Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45172
    Prev
    Next
    INDEX
    Explanations

    confirmation bias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cmp
    -0.09
     Balls
    -0.08
     {}↵↵
    -0.08
     Ball
    -0.08
     pwd
    -0.08
     Locker
    -0.07
     blueprint
    -0.07
     bread
    -0.07
     ball
    -0.07
    -lang
    -0.07
    POSITIVE LOGITS
     favorable
    0.12
     unfavorable
    0.12
     biased
    0.11
     favourable
    0.11
     favorecer
    0.11
    biased
    0.11
     predetermined
    0.10
     favored
    0.10
     agreeable
    0.09
     bias
    0.09
    Activations Density 0.051%

    No Known Activations